{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.91324200913242,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0045662100456621,
      "grad_norm": 7.636920781806111e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0045662100456621,
      "eval_loss": 11.5,
      "eval_runtime": 1.7355,
      "eval_samples_per_second": 212.616,
      "eval_steps_per_second": 53.586,
      "step": 1
    },
    {
      "epoch": 0.0091324200913242,
      "grad_norm": 7.44735516491346e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0136986301369863,
      "grad_norm": 0.0001142916880780831,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 0.0001060927752405405,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0228310502283105,
      "grad_norm": 9.867281187325716e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 9.552860865369439e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0319634703196347,
      "grad_norm": 0.0001116232160711661,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 8.957861427916214e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": 8.468984015053138e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 0.0001123302208725363,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.0502283105022831,
      "grad_norm": 8.9516062871553e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.00012506810890045017,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0593607305936073,
      "grad_norm": 0.00012492881796788424,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.0639269406392694,
      "grad_norm": 0.00013894482981413603,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 0.00011621726298471913,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.00015192000137176365,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.0776255707762557,
      "grad_norm": 0.00014068829477764666,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 0.00015766164870001376,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0867579908675799,
      "grad_norm": 0.0001673324004514143,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 0.0001764104817993939,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0958904109589041,
      "grad_norm": 0.00014649289369117469,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.1004566210045662,
      "grad_norm": 0.00024197340826503932,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.1050228310502283,
      "grad_norm": 0.00016593303007539362,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.00017894427583087236,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.1141552511415525,
      "grad_norm": 0.0002266779338242486,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.1187214611872146,
      "grad_norm": 0.00024604814825579524,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.1232876712328767,
      "grad_norm": 0.00028294420917518437,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 0.00025608166470192373,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.1324200913242009,
      "grad_norm": 0.00026468661963008344,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.0002628884685691446,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.1415525114155251,
      "grad_norm": 0.0002674731658771634,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.0002768425038084388,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.1506849315068493,
      "grad_norm": 0.00020952679915353656,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.1552511415525114,
      "grad_norm": 0.0002470537438057363,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.1598173515981735,
      "grad_norm": 0.0002773989690467715,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.0003815217351075262,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.1689497716894977,
      "grad_norm": 0.00031118819606490433,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.1735159817351598,
      "grad_norm": 0.0003822013968601823,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.1780821917808219,
      "grad_norm": 0.0003194592136424035,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.0003279204829595983,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.1872146118721461,
      "grad_norm": 0.00026009773137047887,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.0003431908262427896,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.1963470319634703,
      "grad_norm": 0.0004453650617506355,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.2009132420091324,
      "grad_norm": 0.00034001778112724423,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 0.00037527232780121267,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.2100456621004566,
      "grad_norm": 0.0005491433548741043,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.2146118721461187,
      "grad_norm": 0.0005592697416432202,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.00044385739602148533,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.2237442922374429,
      "grad_norm": 0.0006460596923716366,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.228310502283105,
      "grad_norm": 0.0005119343986734748,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.228310502283105,
      "eval_loss": 11.5,
      "eval_runtime": 1.7375,
      "eval_samples_per_second": 212.37,
      "eval_steps_per_second": 53.524,
      "step": 50
    },
    {
      "epoch": 0.2328767123287671,
      "grad_norm": 0.0004603175912052393,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.2374429223744292,
      "grad_norm": 0.0004708251217380166,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.2420091324200913,
      "grad_norm": 0.0004849275283049792,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.0005260196630842984,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.2511415525114155,
      "grad_norm": 0.0005645801429636776,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.2557077625570776,
      "grad_norm": 0.0004680722486227751,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.2602739726027397,
      "grad_norm": 0.0005727990646846592,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.2648401826484018,
      "grad_norm": 0.0004610759497154504,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.2694063926940639,
      "grad_norm": 0.0005082708084955812,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.0004806265060324222,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.2785388127853881,
      "grad_norm": 0.0005738113541156054,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.2831050228310502,
      "grad_norm": 0.0006019845022819936,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.2876712328767123,
      "grad_norm": 0.0007565479027107358,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 0.0005941870622336864,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.2968036529680365,
      "grad_norm": 0.0008003446273505688,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": 0.0007270355126820505,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.3059360730593607,
      "grad_norm": 0.0005717016756534576,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.3105022831050228,
      "grad_norm": 0.0008129233028739691,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.3150684931506849,
      "grad_norm": 0.0005562108126468956,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.319634703196347,
      "grad_norm": 0.0008489846368320286,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.3242009132420091,
      "grad_norm": 0.0006689407164230943,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.0006947076180949807,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.0009151662816293538,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.3378995433789954,
      "grad_norm": 0.0007065506069920957,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 0.0009344193967990577,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.3470319634703196,
      "grad_norm": 0.0007428543176501989,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.3515981735159817,
      "grad_norm": 0.0008685676730237901,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": 0.0010367569047957659,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.3607305936073059,
      "grad_norm": 0.00088779121870175,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.0011535785160958767,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.3698630136986301,
      "grad_norm": 0.0007928877021186054,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.3744292237442922,
      "grad_norm": 0.0007278918055817485,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.3789954337899543,
      "grad_norm": 0.0011180439032614231,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.0010650372132658958,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.3881278538812785,
      "grad_norm": 0.0010324729373678565,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.3926940639269406,
      "grad_norm": 0.0013468252727761865,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.3972602739726027,
      "grad_norm": 0.0012604567455127835,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.4018264840182648,
      "grad_norm": 0.0011803044471889734,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.4063926940639269,
      "grad_norm": 0.0011816471815109253,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.0008760665077716112,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.4155251141552511,
      "grad_norm": 0.0013014510041102767,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.4200913242009132,
      "grad_norm": 0.0012484738836064935,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.4246575342465753,
      "grad_norm": 0.000673823815304786,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.4292237442922374,
      "grad_norm": 0.00127010652795434,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.4337899543378995,
      "grad_norm": 0.001143313362263143,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.001319561037234962,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.4429223744292237,
      "grad_norm": 0.0013544725952669978,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.4474885844748858,
      "grad_norm": 0.0012699386570602655,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.4520547945205479,
      "grad_norm": 0.0013309696223586798,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 0.0015540928579866886,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.45662100456621,
      "eval_loss": 11.5,
      "eval_runtime": 1.7035,
      "eval_samples_per_second": 216.609,
      "eval_steps_per_second": 54.593,
      "step": 100
    },
    {
      "epoch": 0.4611872146118721,
      "grad_norm": 0.0016239152755588293,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.4657534246575342,
      "grad_norm": 0.0015479964204132557,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.4703196347031963,
      "grad_norm": 0.0010490111308172345,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.4748858447488584,
      "grad_norm": 0.0013949101557955146,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 0.0016831792891025543,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.4840182648401826,
      "grad_norm": 0.0014860843075439334,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.4885844748858447,
      "grad_norm": 0.0016424607019871473,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.0009544173954054713,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.4977168949771689,
      "grad_norm": 0.0015220168279483914,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.502283105022831,
      "grad_norm": 0.0014989678747951984,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.5068493150684932,
      "grad_norm": 0.002048507798463106,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.5114155251141552,
      "grad_norm": 0.0013840971514582634,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.5159817351598174,
      "grad_norm": 0.0019008719827979803,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.5205479452054794,
      "grad_norm": 0.001142954803071916,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.5251141552511416,
      "grad_norm": 0.001257114578038454,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.5296803652968036,
      "grad_norm": 0.001405723625794053,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.5342465753424658,
      "grad_norm": 0.001302759745158255,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.5388127853881278,
      "grad_norm": 0.0010542668169364333,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.54337899543379,
      "grad_norm": 0.0015165412332862616,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.0015218885382637382,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.5525114155251142,
      "grad_norm": 0.0017859709914773703,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.5570776255707762,
      "grad_norm": 0.002248491160571575,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.5616438356164384,
      "grad_norm": 0.0018909923965111375,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.5662100456621004,
      "grad_norm": 0.0017317014280706644,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.5707762557077626,
      "grad_norm": 0.00205090269446373,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.5753424657534246,
      "grad_norm": 0.0023619700223207474,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.5799086757990868,
      "grad_norm": 0.0022807633504271507,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.5844748858447488,
      "grad_norm": 0.0024749066215008497,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.589041095890411,
      "grad_norm": 0.0021680218633264303,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.593607305936073,
      "grad_norm": 0.002179680857807398,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.5981735159817352,
      "grad_norm": 0.0019888917449861765,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.0019640163518488407,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.6073059360730594,
      "grad_norm": 0.0017146794125437737,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.6118721461187214,
      "grad_norm": 0.001860221615061164,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.0018664604285731912,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.6210045662100456,
      "grad_norm": 0.0019662403501570225,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.6255707762557078,
      "grad_norm": 0.002076753880828619,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.6301369863013698,
      "grad_norm": 0.0016036474844440818,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.634703196347032,
      "grad_norm": 0.0017104905564337969,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 0.0020441217347979546,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.6438356164383562,
      "grad_norm": 0.0026159256231039762,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.6484018264840182,
      "grad_norm": 0.0026722934562712908,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.6529680365296804,
      "grad_norm": 0.001849271240644157,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.0015774924540892243,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.6621004566210046,
      "grad_norm": 0.001427516690455377,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.002902843989431858,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.6712328767123288,
      "grad_norm": 0.0017904357519000769,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.6757990867579908,
      "grad_norm": 0.0017669800436124206,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.680365296803653,
      "grad_norm": 0.002602022374048829,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.002478090114891529,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.684931506849315,
      "eval_loss": 11.5,
      "eval_runtime": 1.6892,
      "eval_samples_per_second": 218.444,
      "eval_steps_per_second": 55.055,
      "step": 150
    },
    {
      "epoch": 0.6894977168949772,
      "grad_norm": 0.0015991757391020656,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.6940639269406392,
      "grad_norm": 0.0025215165223926306,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.6986301369863014,
      "grad_norm": 0.002266379538923502,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.7031963470319634,
      "grad_norm": 0.001956170191988349,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.7077625570776256,
      "grad_norm": 0.001797800650820136,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.002070017158985138,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.7168949771689498,
      "grad_norm": 0.0022779679857194424,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.7214611872146118,
      "grad_norm": 0.0022892688866704702,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.726027397260274,
      "grad_norm": 0.002369545865803957,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 0.0018990531098097563,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.7351598173515982,
      "grad_norm": 0.0018017939291894436,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.7397260273972602,
      "grad_norm": 0.001268142950721085,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.7442922374429224,
      "grad_norm": 0.001859299256466329,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.7488584474885844,
      "grad_norm": 0.001720873056910932,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 0.0014712800038978457,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.7579908675799086,
      "grad_norm": 0.0033800657838582993,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.7625570776255708,
      "grad_norm": 0.0016922298818826675,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.002227977616712451,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.771689497716895,
      "grad_norm": 0.0032129210885614157,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.776255707762557,
      "grad_norm": 0.0030342095997184515,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.7808219178082192,
      "grad_norm": 0.0020047000143676996,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.7853881278538812,
      "grad_norm": 0.0015817369567230344,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.7899543378995434,
      "grad_norm": 0.0018114951672032475,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.7945205479452054,
      "grad_norm": 0.0018707645358517766,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.7990867579908676,
      "grad_norm": 0.0016957343323156238,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.8036529680365296,
      "grad_norm": 0.0025184564292430878,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.8082191780821918,
      "grad_norm": 0.0023704906925559044,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.8127853881278538,
      "grad_norm": 0.0025631284806877375,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.817351598173516,
      "grad_norm": 0.0016029763501137495,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.0018653357401490211,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.8264840182648402,
      "grad_norm": 0.0020969025790691376,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.8310502283105022,
      "grad_norm": 0.002198559930548072,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.8356164383561644,
      "grad_norm": 0.002463407814502716,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.8401826484018264,
      "grad_norm": 0.0030100273434072733,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.8447488584474886,
      "grad_norm": 0.0026026591658592224,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.8493150684931506,
      "grad_norm": 0.0019296645186841488,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.8538812785388128,
      "grad_norm": 0.0017289838287979364,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.8584474885844748,
      "grad_norm": 0.0023671514354646206,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.863013698630137,
      "grad_norm": 0.002475269138813019,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.867579908675799,
      "grad_norm": 0.002543459413573146,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.8721461187214612,
      "grad_norm": 0.0023066180292516947,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.0018597402377054095,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.8812785388127854,
      "grad_norm": 0.002305945148691535,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.8858447488584474,
      "grad_norm": 0.002441455377265811,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 0.001650617690756917,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.8949771689497716,
      "grad_norm": 0.0020209187641739845,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.8995433789954338,
      "grad_norm": 0.0015854135854169726,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.9041095890410958,
      "grad_norm": 0.0014424327528104186,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.908675799086758,
      "grad_norm": 0.002386372070759535,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 0.0026080580428242683,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.91324200913242,
      "eval_loss": 11.5,
      "eval_runtime": 1.7515,
      "eval_samples_per_second": 210.672,
      "eval_steps_per_second": 53.096,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32158462771200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}